Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    puede
    0.88
    odiac
    0.84
     μπορεί
    0.83
    缀
    0.80
     poden
    0.77
    बारक
    0.76
    arem
    0.73
     smash
    0.71
     मोहन
    0.71
     smashing
    0.70
    POSITIVE LOGITS
     the
    1.13
     őket
    1.01
     fhe
    0.96
    С
    0.93
     it
    0.92
     them
    0.92
    ТЕ
    0.90
    ر
    0.90
     this
    0.90
    ي
    0.87
    Act Density 4.977%

    No Known Activations